LumpMap 3D

The description states that LumpMap 3D is an anatomy-first educational navigator for common visible or palpable superficial lumps. It offers three ways to begin: describing a concern in everyday English, Urdu, or Roman Urdu; exploring a rotatable 3D body and selecting one of seventeen body regions; or comparing different conditions at the same beneath-the-skin scale.

It contains fourteen curated condition families (e.g., epidermoid cysts, folliculitis, ingrown hairs) with distinct procedural 3D scenes, three educational stages, condition patterns, care information, risk reduction strategies, and visible medical sources. Users complete an eight-stage guided flow covering location, depth, timing, pain, surface inflammation, recurrence patterns, whole-body symptoms, and relevant context.

Results place safety before educational comparisons and use four care levels: emergency, same-day urgent, prompt appointment, or no urgent pattern identified. A factual Visit Note contains only information the user actually supplied.

The system is built with Next.js, React, TypeScript, React Three Fiber, Three.js, Motion, Zod, and the OpenAI Responses API. The 3D anatomy is procedural — assembled in code rather than downloaded as opaque models.

Inference The product appears to be a prototype or proof-of-concept application focused on education and navigation, not diagnosis.

The author claims that LumpMap 3D replaces false certainty with understandable anatomy, care-navigation guidance, and better questions. It addresses the confusion people have when using words like "cyst", "daana", "phinsi", etc., to describe different conditions.

It explicitly states it is not a diagnostic system — it never says “you have X,” provides probabilities, or rules out serious causes through visual/text matching.

Inference The positioning reflects an intent to offer clarity and safety in health communication, especially for non-experts dealing with ambiguous symptoms. It positions itself as a tool for empowerment rather than authority.

The description does not name specific customer segments or personas. However, it implies that the target includes individuals who experience lumps and are uncertain about what they might represent — particularly those seeking guidance before seeing a clinician.

It supports multilingual input (English, Urdu, Roman Urdu) and is designed for small screens and accessibility considerations, suggesting a broad consumer audience with varying technical comfort levels.

Inference The ICP likely includes general consumers who want to better understand lumps or skin concerns, especially in multilingual contexts where terminology is imprecise. The product may also appeal to health educators or clinicians looking for tools to assist patients.

There is no evidence of a business model or pricing strategy in the description. The author does not mention monetization, subscriptions, partnerships, or any revenue-generating mechanism.

Inference The project appears to be a personal or hackathon effort without commercial intent at this stage.

LumpMap 3D is built with Next.js, React, TypeScript, React Three Fiber, Three.js, Motion, Zod, and the OpenAI Responses API. It uses procedural 3D rendering instead of pre-built models.

GPT-5.6 is used only for converting everyday language into structured symptom records. Structured Outputs, server-only keys, request-size limits, and privacy-preserving abuse controls are implemented to manage AI use safely.

Deterministic local code evaluates urgency, ranks comparisons, produces care copy, and generates the Visit Note — ensuring that no model sets or reduces urgency.

The application is deployed on Vercel from a public GitHub repository. It includes browser-based accessibility QA, responsive design, keyboard controls, reduced motion support, and fallbacks for non-WebGL environments.

Inference The technical stack suggests a modern web app with strong emphasis on safety and determinism in medical decision-making. The use of AI is limited to structured input processing, while outputs are governed by local logic.

There is no evidence of traction or user adoption beyond the author’s own account. No customers, revenue, usage metrics, or performance data are provided.

The project was submitted to a hackathon and is described as a complete, coherent consumer product rather than a proof-of-concept.

Inference No maturity signals exist in the description — it remains unclear whether this has moved beyond prototype status or been tested with real users.

There is no mention of competitors or competitive landscape. The author does not reference existing tools for lump identification, skin condition education, or 3D anatomy visualization.

Inference The competitive environment is unknown based on the provided information.

• Unverified safety claims: The system relies heavily on deterministic logic to prevent AI from making medical decisions. However, there’s no independent validation of these safeguards.
• No user feedback or testing data: There is no evidence that the product has been tested with real users or clinicians.
• Limited scope and localization: The current atlas includes only fourteen conditions and seventeen body regions; expansion plans depend on clinician review and localization.
• Self-reported nature: All claims are unverified, including functionality, safety, and usability.

Inference The lack of external validation, user testing, or clinical oversight raises significant concerns about real-world applicability and safety.

1. Has the product been tested with actual users or clinicians?
2. What specific safety measures are in place to prevent misinterpretation or misuse?
3. How does the team plan to scale beyond the current 14 conditions and 17 regions?
4. Are there any plans for monetization or long-term sustainability?
5. What is the process for validating new content or updating existing ones?
6. Have you considered accessibility compliance (e.g., WCAG)?
7. How do you handle edge cases or rare phrases that might not be covered by your schema?